I’m Felipe, a PhD chemist (computational chemistry) and software developer. This is where I (try to) organize my thoughts and ideas on various topics.
⚛️ Check out
overreact, the computational predictor for complex chemical reactions I maintain, developed at @geem-lab. Click here to learn more about this exciting project!
I work at Cellertz Bio, a company revolutionizing molecule discovery through generative biology. Views expressed are my own.
I have recently released the initial version of the chat-splitter crate. The purpose of this blog post is to offer an overview of what chat-splitter is, the issue it addresses, and how it operates. The context length problem Large language models face challenges when processing lengthy sequences of text. State-of-the-art models, like OpenAI’s GPT-4, have a maximum token limit that restricts their ability to handle contexts beyond a certain threshold. The maximum context window typically ranges from 2k tokens for legacy GPT-3 models to as high as 32k tokens for the most recent GPT-4 model, and potentially more1....